基于模糊神经网络与主成分分析的磨削表面粗糙度在线预测

doi:10.3969/j.issn.1000-1158.2022.11.01

摘要
图/表
参考文献(27)
相关文章 (15)

全文: PDF (3230 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要基于声发射和振动信号提出了一种模糊神经网络和主成分分析的表面粗糙度预测方法,以提高磨削过程中工件表面粗糙度识别的准确性。首先,采集磨削程中声发射与振动信号,提取相关时域特征、频域特征和小波包特征参数,利用主成分分析对特征量进行降维优化;然后,构建表面粗糙度模糊神经网络预测模型,将信号特征量与表面粗糙度作为模糊神经网络的输入和输出;最后,对模型进行训练,并对表面粗糙度预测精度进行验证。实验结果表明:通过主成分分析(PCA)方法对声发射和振动信号特征量进行降维得到5个主成分,以此建立的模糊神经网络表面粗糙度预测模型的效果精度可达到91%以上,与局部线性嵌入和多维标度法降维方法相比,PCA方法降维后的特征所含信息更优,预测准确度更高。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	迟玉伦
	吴耀宇
	江欢
	杨磊

关键词 ：计量学, 表面粗糙度, 在线预测, 主成分分析, 模糊神经网络, 磨削

Abstract：Based on acoustic emission and vibration signals, a surface roughness prediction method is proposed to improve the accuracy of workpiece surface roughness identification in grinding process by using the fuzzy neural network and the principal component analysis. Firstly, the acoustic emission and vibration signals are measured in the grinding process, and the relevant time-domain features, the frequency-domain features and the wavelet packet feature parameters are extracted from these signals. The extracted feature parameters are reduced and optimized by using principal component analysis. Then, the fuzzy neural network prediction model of surface roughness is constructed, and the signal feature parameters and the surface roughness are taken as the input and output of the prediction model. Finally, the model is used and trained to verify the prediction accuracy of surface roughness model. The experimental results show that five principal components of the acoustic emission and vibration signal feature parameters are reduced and obtained by using the principal component analysis (PCA) method. Based on the five principal components, the effect accuracy of the fuzzy neural network surface roughness prediction model can reach more than 91%. Compared with locally linear embedding and multidimensional scaling methods, the PCA method is better, and the prediction accuracy is higher.

Key words： metrology surface roughness on-line prediction PCA fuzzy neural network grinding

收稿日期: 2021-08-03 发布日期: 2022-11-14

PACS:

TB92

基金资助:上海市科学技术委员会科研计划项目(17DZ2283300)

作者简介: 迟玉伦(1983-),黑龙江穆棱人,上海理工大学高级实验师,从事现代制造技术研究。Email:chiyulun@163.com

引用本文:

迟玉伦,吴耀宇,江欢,杨磊. 基于模糊神经网络与主成分分析的磨削表面粗糙度在线预测[J]. 计量学报, 2022, 43(11): 1389-1397.
CHI Yu-lun,WU Yao-yu,JIANG Huan,YANG Lei. On-line Prediction of Grinding Surface Roughness Based on Fuzzy Neural Network and Principal Component Analysis. Acta Metrologica Sinica, 2022, 43(11): 1389-1397.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2022.11.01 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2022/V43/I11/1389

［1］李晓梅, 丁宁, 朱喜林. 表面粗糙度模糊神经网络在线辨识模型［J］. 机械工程学报, 2007, 43(3):212-217.
Li X M, Ding N, Zhu X L. Surface roughness fuzzy neural network online identification model ［J］. Chinese Journal of Mechanical Engineering, 2007, 43(3):212-217.
［2］汪朝海, 蔡晋辉, 曾九孙. 基于经验模态分解和主成分分析的滚动轴承故障诊断研究［J］. 计量学报, 2019, 40(6):1077-1082.
Wang C H, Cai J H, ZENG J S, Research on Fault Diagnosis of Rolling Bearing Based on Empirical Mode Decomposition and Principal Component Analysis ［J］. Acta Metrologica Sinica, 2019, 40(6):1077-1082.
［3］王政平, 张锡芳, 张艳娥. 表面粗糙度光学测量方法研究进展［J］. 传感器与微系统, 2007, 26(9):4-6.
Wang Z P, Zhang X F, Zhang Y E. Research progress of optical measurement methods for surface. Transducer and Microsystem Technologies, 2007, 26(9):4-6.
［4］刘晨, 卢荣胜, 陈磊,等. 基于光学法表面粗糙度的测量研究进展［J］. 半导体光电, 2010, 31(4):495-500.
Liu C, Lu R S, Chen L, et al. Research progress in surface roughness measurement based on optical methods ［J］. Semiconductor Optoelectronics, 2010, 31(4):495-500.
［5］Salgado D R, Alonso F J, Cambero I, et al. In-process surface roughness prediction system using cutting vibrations in turning ［J］. The International Journal of Advanced Manufacturing Technology, 2009, 43(1/2):40-51.
［6］Lauro C H, Brandao L C, Baldo D, et al. Monitoring and processing signal applied in machining processes:a review ［J］. Measurement, 2014, 58:73-86.
［7］Ozel T, Karpat Y, Luis Figueira, et al. Modelling of surface finish and tool flank wear in turning of AISI D2 steel with ceramic wiper inserts ［J］. Journal of Materials Processing Technology, 2007, 189(1-3):192-198.
［8］迟军, 陈廉清, 杨超珍. 基于小波包分析和Elman网络的切削表面粗糙度预测方法［J］. 中国机械工程, 2010(7):822-826.
Chi J, Chen L Q, Yang C Z. Cutting surface roughness prediction method based on wavelet packet analysis and Elman network ［J］. China Mechanical Engineering, 2010(7):822-826.
［9］Upadhyay V, Jain P K, Mehta N K. In-process prediction of surface roughness in turning of Ti-6Al-4V alloy using cutting parameters and vibration signals ［J］. Measurement, 2013, 46(1):154-160.
［10］Risbood K A, Dixit U S, Sahasrabudhe A D. Prediction of surface roughness and dimensional deviation by measuring cutting forces and vibrations in turning process ［J］. Journal of Materials Processing Tech, 2003, 132(1):203-214.
［11］Plaza E G, Lopezp J N. Surface roughness monitoring by singular spectrum analysis of vibration signals ［J］. Mechanical Systems and Signal Processing, 2017, 84:516-530.
［12］胡仲翔, 滕家绪, 钱耀川,等. 用声发射信号和改进的BP神经网络预测磨削表面粗糙度［J］. 装甲兵工程学院学报, 2009, 23(6):76-79.
Hu Z X, Teng J X, Qian Y C et al. Using Acoustic Emission Signal and Improved BP Neural Network to Predict Grinding Surface Roughness ［J］. Journal of Armored Forces Engineering Academy, 2009, 23(6):76-79
［13］王艳, 王建波, 王强,等. 利用声发射信号时频特征在线监测慢走丝线切割加工表面粗糙度［J］. 光学精密工程, 2017, 25(8):2090-2097.
Wang Y, Wang J B, Wang Q, et al. Using the time-frequency characteristics of acoustic emission signals to monitor the surface roughness of slow-moving wire cutting on-line ［J］. Optics and Precision Engineering, 2017, 25(8):2090-2097.
［14］郭力, 邓喻. 采用遗传算法优化神经网络的铸铁表面粗糙度声发射预测［J］. 机械科学与技术, 2018, 37(10):1512-1516.
Guo L, Deng Y. Using genetic algorithm to optimize neural network for acoustic emission prediction of cast iron surface roughness［J］. Mechanical Science and Technology, 2018, 37(10):1512-1516.
［15］孙林, 杨世元. 基于最小二乘支持矢量机的成形磨削表面粗糙度预测及磨削用量优化设［J］. 机械工程学报, 2009, 45( 10) :254－260.
Sun L, Yang S Y. Form grinding surface roughness prediction and grinding parameter optimization design based on least squares support vector machine［J］. Journal of Mechanical Engineering, 2009, 45(10):254-260.
［16］汪振华, 赵成刚, 袁军堂,等. 高速铣削AlMn1Cu表面粗糙度变化规律及铣削参数优化研究［J］. 南京理工大学学报(自然科学版), 2010, 34(4):537-542.
Wang Z H, Zhao C G, Yuan J T, et al. High-speed milling AlMn1Cu surface roughness variation law and milling parameter optimization research ［J］. Journal of Nanjing University of Science and Technology (Natural Science Edition), 2010, 34(4):537-542.
［17］陈廉清, 郭建亮, 杨勋,等. 基于进化神经网络的磨削粗糙度预测模型［J］. 计算机集成制造系统, 2013, 19( 11) :2854-2863.
Chen L, Guo J L, Yang X, et al. Grinding roughness prediction model based on evolutionary neural network［J］. Computer Integrated Manufacturing System, 2013, 19(11):2854-2863.
［18］郑刚, 马旌超, 吴雁,等. 基于模糊预测的铣削工艺参数优选方法研究［J］. 组合机床与自动化加工技术. 2020, 01(1):136-140.
Zheng G, Ma J C, Wu Y, et al. Research on optimization method of milling process parameters based on fuzzy prediction ［J］. Modular Machine Tool and Automatic Processing Technology. 2020, 01(1):136-140.
［19］刘蒲生. 高速磨削［M］. 北京:机械工业出版社, 1982.
［20］任敬心, 华定安. 磨削原理［M］. 西安:西北工业大学出版社, 1988.
［21］Makhutov N A. Acoustic Emission Analysis of Deformation and Damage Processes［J］. Inorganic materials, 2019, 55(15):1511-1515.
［22］朱建新, 吕宝林, 乔松,等. 基于主成分分析及多维高斯贝叶斯的超声流量计故障智能诊断方法［J］. 计量学报, 2020, 41(12):1494-1499.
Zhu J X, Lv B L, Qiao S, et al. Application of Primary Component Analysis and Multivariate Gaussian Bayesian Method on Intelligent Failure Diagnosis of Ultrasonic Flowmeter ［J］. Acta Metrologica Sinica, 2020, 41(12):1494-1499.
［23］李舜酩, 郭海东, 李殿荣. 振动信号处理方法综述［J］. 仪器仪表学报. 2013, 34(8):1907-1915.
Li S M, Guo H D, Li D R. Overview of vibration signal processing methods ［J］. Chinese Journal of Scientific Instrument. 2013, 34(8):1907-1915.
［24］Li W, Zhi L, Qiang W, et al. ELM_Kernel and Wavelet Packet Decomposition Based EEG Classification Algorithm. Automatic Control and Computer Sciences, 2019, 53(5):452-460.
［25］Yang C Y, Wu T Y. Diagnostics of gear deterioration sing EEMD approach and PCA process ［J］. Measurement, 2015, 61(2):75-87.
［26］Paulo V C S, Luiz C B T, Augusto J G, et al. Data density-based clustering for regularized fuzzy neural networks based on nullneurons and robust activation function. IEEE Symposium on Computer Applications & Industrial Electronics, 2019, 23(23):12475-12489.
［27］Giovanni D L, Massi G, Pezzella F. An adaptive genetic algorithm for large-size open stack problems. International Journal of Production Research, 2013, 51(3):682-697.